ASCFL:Accurate and Speedy Semi-Supervised Clustering Federated Learning  

作　　者：Jingyi He Biyao Gong Jiadi Yang Hai Wang Pengfei Xu Tianzhang Xing 

机构地区：[1]School of Information Science and Technology,Northwest University,Xi’an 710100,China [2]Internet of Things Research Center,Northwest University,Xi’an 710100,China

出　　处：《Tsinghua Science and Technology》2023年第5期823-837,共15页清华大学学报（自然科学版（英文版）

基　　金：supported by the National Key Research and Development Program of China(No.2019YFC1520904);the National Natural Science Foundation of China(No.61973250).

摘　　要：The influence of non-Independent Identically Distribution(non-IID)data on Federated Learning(FL)has been a serious concern.Clustered Federated Learning(CFL)is an emerging approach for reducing the impact of non-IID data,which employs the client similarity calculated by relevant metrics for clustering.Unfortunately,the existing CFL methods only pursue a single accuracy improvement,but ignore the convergence rate.Additionlly,the designed client selection strategy will affect the clustering results.Finally,traditional semi-supervised learning changes the distribution of data on clients,resulting in higher local costs and undesirable performance.In this paper,we propose a novel CFL method named ASCFL,which selects clients to participate in training and can dynamically adjust the balance between accuracy and convergence speed with datasets consisting of labeled and unlabeled data.To deal with unlabeled data,the prediction labels strategy predicts labels by encoders.The client selection strategy is to improve accuracy and reduce overhead by selecting clients with higher losses participating in the current round.What is more,the similarity-based clustering strategy uses a new indicator to measure the similarity between clients.Experimental results show that ASCFL has certain advantages in model accuracy and convergence speed over the three state-of-the-art methods with two popular datasets.

关 键 词：federated learning clustered federated learning non-Independent Identically Distribution(non-IID)data similarity indicator client selection semi-supervised learning 

分 类 号：P20[天文地球—测绘科学与技术]